commit 29a2142efce495c983be4a3b25390442a409d65e Author: ModelHub XC Date: Sun Apr 12 03:25:56 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/SmolLM2-360M-Rickified-GRPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0107d66 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +SmolLM2-360M-Rickified-GRPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-360M-Rickified-GRPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-360M-Rickified-GRPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-360M-Rickified-GRPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-360M-Rickified-GRPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-360M-Rickified-GRPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-360M-Rickified-GRPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-360M-Rickified-GRPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-360M-Rickified-GRPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-360M-Rickified-GRPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-360M-Rickified-GRPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-360M-Rickified-GRPO.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..026d9b9 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: chrishoertnagl/SmolLM2-360M-Rickified-GRPO +datasets: qgallouedec/rick-physics-grpo +language: +- en +library_name: transformers +model_name: SmolLM2-360M-Rickified-GRPO +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- grpo +--- +## About + + + + + + + + + +static quants of https://huggingface.co/chrishoertnagl/SmolLM2-360M-Rickified-GRPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#SmolLM2-360M-Rickified-GRPO-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-360M-Rickified-GRPO-GGUF/resolve/main/SmolLM2-360M-Rickified-GRPO.Q2_K.gguf) | Q2_K | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-360M-Rickified-GRPO-GGUF/resolve/main/SmolLM2-360M-Rickified-GRPO.Q3_K_S.gguf) | Q3_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-360M-Rickified-GRPO-GGUF/resolve/main/SmolLM2-360M-Rickified-GRPO.IQ4_XS.gguf) | IQ4_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-360M-Rickified-GRPO-GGUF/resolve/main/SmolLM2-360M-Rickified-GRPO.Q3_K_M.gguf) | Q3_K_M | 0.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-360M-Rickified-GRPO-GGUF/resolve/main/SmolLM2-360M-Rickified-GRPO.Q3_K_L.gguf) | Q3_K_L | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-360M-Rickified-GRPO-GGUF/resolve/main/SmolLM2-360M-Rickified-GRPO.Q4_K_S.gguf) | Q4_K_S | 0.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-360M-Rickified-GRPO-GGUF/resolve/main/SmolLM2-360M-Rickified-GRPO.Q4_K_M.gguf) | Q4_K_M | 0.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-360M-Rickified-GRPO-GGUF/resolve/main/SmolLM2-360M-Rickified-GRPO.Q5_K_S.gguf) | Q5_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-360M-Rickified-GRPO-GGUF/resolve/main/SmolLM2-360M-Rickified-GRPO.Q5_K_M.gguf) | Q5_K_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-360M-Rickified-GRPO-GGUF/resolve/main/SmolLM2-360M-Rickified-GRPO.Q6_K.gguf) | Q6_K | 0.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-360M-Rickified-GRPO-GGUF/resolve/main/SmolLM2-360M-Rickified-GRPO.Q8_0.gguf) | Q8_0 | 0.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-360M-Rickified-GRPO-GGUF/resolve/main/SmolLM2-360M-Rickified-GRPO.f16.gguf) | f16 | 0.8 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + + diff --git a/SmolLM2-360M-Rickified-GRPO.IQ4_XS.gguf b/SmolLM2-360M-Rickified-GRPO.IQ4_XS.gguf new file mode 100644 index 0000000..c7b4e20 --- /dev/null +++ b/SmolLM2-360M-Rickified-GRPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40b67bb1637cbb476118aa380464cd01d39ffe2d90cb80a7549bd927993be57b +size 228197920 diff --git a/SmolLM2-360M-Rickified-GRPO.Q2_K.gguf b/SmolLM2-360M-Rickified-GRPO.Q2_K.gguf new file mode 100644 index 0000000..6f54ab1 --- /dev/null +++ b/SmolLM2-360M-Rickified-GRPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d267782bac46f6e2f608ef82c653e95b360e8eb11ac2476faa690df334c6749 +size 218674720 diff --git a/SmolLM2-360M-Rickified-GRPO.Q3_K_L.gguf b/SmolLM2-360M-Rickified-GRPO.Q3_K_L.gguf new file mode 100644 index 0000000..7d93404 --- /dev/null +++ b/SmolLM2-360M-Rickified-GRPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0763727ea30091cba5f7958084775def2cb39d1c86911cbed29183afff023ad7 +size 246322720 diff --git a/SmolLM2-360M-Rickified-GRPO.Q3_K_M.gguf b/SmolLM2-360M-Rickified-GRPO.Q3_K_M.gguf new file mode 100644 index 0000000..fafd2ed --- /dev/null +++ b/SmolLM2-360M-Rickified-GRPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:026af13bb47b8d45ded16ac39249b1f2422fbdcb4c943f06916a9b45c5e78ae6 +size 234687520 diff --git a/SmolLM2-360M-Rickified-GRPO.Q3_K_S.gguf b/SmolLM2-360M-Rickified-GRPO.Q3_K_S.gguf new file mode 100644 index 0000000..7d773d6 --- /dev/null +++ b/SmolLM2-360M-Rickified-GRPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a9feab04ef9b99b096a05da59613ab41c16595c64e8af746273b96aea51e672 +size 218674720 diff --git a/SmolLM2-360M-Rickified-GRPO.Q4_K_M.gguf b/SmolLM2-360M-Rickified-GRPO.Q4_K_M.gguf new file mode 100644 index 0000000..76bdcc8 --- /dev/null +++ b/SmolLM2-360M-Rickified-GRPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:461aa87ce609c8f9b5c842850de5662c62f386f939d0e1d0bb2e162b396f041b +size 270591520 diff --git a/SmolLM2-360M-Rickified-GRPO.Q4_K_S.gguf b/SmolLM2-360M-Rickified-GRPO.Q4_K_S.gguf new file mode 100644 index 0000000..a3ceabd --- /dev/null +++ b/SmolLM2-360M-Rickified-GRPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fab89486cb8e3381b54d66b7a6a02d7a00ade4563b880c7df4378e006ca37e0a +size 259916320 diff --git a/SmolLM2-360M-Rickified-GRPO.Q5_K_M.gguf b/SmolLM2-360M-Rickified-GRPO.Q5_K_M.gguf new file mode 100644 index 0000000..7b6b336 --- /dev/null +++ b/SmolLM2-360M-Rickified-GRPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5ef70dfb80cfebb8f78b3ac0953b8e905656a67e5f1db71f07b037c9545c388 +size 289945120 diff --git a/SmolLM2-360M-Rickified-GRPO.Q5_K_S.gguf b/SmolLM2-360M-Rickified-GRPO.Q5_K_S.gguf new file mode 100644 index 0000000..d3f829f --- /dev/null +++ b/SmolLM2-360M-Rickified-GRPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ece017e8a1a221088f6534442ad365739805c9ae20e47644184ddc91d502e835 +size 283186720 diff --git a/SmolLM2-360M-Rickified-GRPO.Q6_K.gguf b/SmolLM2-360M-Rickified-GRPO.Q6_K.gguf new file mode 100644 index 0000000..ff86a76 --- /dev/null +++ b/SmolLM2-360M-Rickified-GRPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a151fd7628910631fbff385406afb9b70be91404d24d68cb65a6f6d76c968ce5 +size 367359520 diff --git a/SmolLM2-360M-Rickified-GRPO.Q8_0.gguf b/SmolLM2-360M-Rickified-GRPO.Q8_0.gguf new file mode 100644 index 0000000..4e53057 --- /dev/null +++ b/SmolLM2-360M-Rickified-GRPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d19f5a16dc24f47eafb55b8015f19b477db11e57a9fa0d0c1fbb5fa83351e7d +size 386405920 diff --git a/SmolLM2-360M-Rickified-GRPO.f16.gguf b/SmolLM2-360M-Rickified-GRPO.f16.gguf new file mode 100644 index 0000000..247a57d --- /dev/null +++ b/SmolLM2-360M-Rickified-GRPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c863d3a4468fa56317d0548976b436a618a675a7cc7ffe0022494fefe2a2055 +size 725554720